Análisis de modelos SOM - Frecuencia datos de entrada: semana

Modelo

• ID: 137
• Descripción:
• Frecuencia: semana
• Variables: fecha_cnt, tmax, tmin, precip, longitud, latitud, altitud
• Dimensiones del mapa: 5,5
• Iteraciones: 1000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-137.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 156652 objects.
Mean distance to the closest unit in the map: 1.227.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_semana_2k.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt          tmax       
 Length:156652      Length:156652      Min.   : 1.00   Min.   :-109.0  
 Class :character   Class :character   1st Qu.:13.00   1st Qu.: 147.0  
 Mode  :character   Mode  :character   Median :27.00   Median : 201.0  
                                       Mean   :26.53   Mean   : 202.1  
                                       3rd Qu.:40.00   3rd Qu.: 262.0  
                                       Max.   :53.00   Max.   : 442.0  
      tmin             precip           nevada    prof_nieve      
 Min.   :-189.00   Min.   :  0.00   Min.   :0   Min.   :   0.000  
 1st Qu.:  48.00   1st Qu.:  0.00   1st Qu.:0   1st Qu.:   0.000  
 Median :  98.00   Median :  3.00   Median :0   Median :   0.000  
 Mean   :  98.13   Mean   : 16.92   Mean   :0   Mean   :   0.604  
 3rd Qu.: 152.00   3rd Qu.: 20.00   3rd Qu.:0   3rd Qu.:   0.000  
 Max.   : 272.00   Max.   :690.00   Max.   :0   Max.   :1073.000  
    longitud        latitud           altitud      
 Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:39.01   1st Qu.: -4.850   1st Qu.:  44.0  
 Median :41.22   Median : -1.411   Median : 263.0  
 Mean   :40.05   Mean   : -2.426   Mean   : 478.5  
 3rd Qu.:42.19   3rd Qu.:  1.272   3rd Qu.: 687.0  
 Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

    1     2     3     4     5     6     7     8     9    10    11    12    13 
 1120  5161  6409  7482  3008  8641  6344 10804  7674  1298  7701  8299  3942 
   14    15    16    17    18    19    20    21    22    23    24    25 
 4317   933 13215  9828  6971  6927  3389  6621  4704  4241  8076  9547 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "precip", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

      fecha_cnt       tmax       tmin      precip  longitud   latitud
[1,] 0.08432857 -0.7469848 -0.7842133  0.41799419 0.4894182 0.2265599
[2,] 0.89786174  0.3009610  0.2987476 -0.02755607 0.2177896 0.2643051
         altitud
[1,]  0.32418276
[2,] -0.03335556

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   altitud      tmax   latitud fecha_cnt      tmin    precip 
0.9451666 0.9283950 0.9045293 0.9042700 0.9010965 0.8970326 0.8632285 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : -3.0   Min.   :-51.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:149.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.29   Mean   :229.6   Mean   :165.2   Mean   :  5.422   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :167.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.03   Mean   : 369.5  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-31.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.:14.00   1st Qu.:152.0   1st Qu.:  52.00   1st Qu.:  0.00   1st Qu.:0  
 Median :27.00   Median :203.0   Median :  99.00   Median :  3.00   Median :0  
 Mean   :26.54   Mean   :208.5   Mean   :  99.39   Mean   : 16.63   Mean   :0  
 3rd Qu.:40.00   3rd Qu.:267.0   3rd Qu.: 148.00   3rd Qu.: 20.00   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   : 272.00   Max.   :690.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:39.56   1st Qu.: -4.488   1st Qu.:  52.0  
 Median :  0.0000   Median :41.29   Median : -1.293   Median : 258.0  
 Mean   :  0.0815   Mean   :40.73   Mean   : -1.677   Mean   : 374.5  
 3rd Qu.:  0.0000   3rd Qu.:42.12   3rd Qu.:  1.296   3rd Qu.: 639.0  
 Max.   :685.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin              precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.000   Min.   :  0.00  
 1st Qu.:13.00   1st Qu.:  26.00   1st Qu.: -36.000   1st Qu.:  4.00  
 Median :26.00   Median :  70.00   Median :   5.000   Median : 21.00  
 Mean   :26.51   Mean   :  74.19   Mean   :   6.032   Mean   : 33.88  
 3rd Qu.:41.00   3rd Qu.: 124.00   3rd Qu.:  52.000   3rd Qu.: 49.00  
 Max.   :53.00   Max.   : 232.00   Max.   : 148.000   Max.   :256.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.2717  
 Mean   :0   Mean   :   9.254   Mean   :42.29   Mean   :  0.8465  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   : 953  
 1st Qu.:1971  
 Median :2247  
 Mean   :2187  
 3rd Qu.:2400  
 Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : -3.0   Min.   :-51.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:149.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.29   Mean   :229.6   Mean   :165.2   Mean   :  5.422   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :167.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.03   Mean   : 369.5  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-31.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.:14.00   1st Qu.:153.0   1st Qu.:  52.00   1st Qu.:  0.00   1st Qu.:0  
 Median :27.00   Median :204.0   Median :  99.00   Median :  3.00   Median :0  
 Mean   :26.51   Mean   :208.8   Mean   :  99.46   Mean   : 15.16   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:267.0   3rd Qu.: 149.00   3rd Qu.: 19.00   3rd Qu.:0  
 Max.   :53.00   Max.   :442.0   Max.   : 272.00   Max.   :172.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :28.46   Min.   :-16.329   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:39.56   1st Qu.: -4.488   1st Qu.:  52.0  
 Median :  0.00000   Median :41.29   Median : -1.293   Median : 258.0  
 Mean   :  0.06592   Mean   :40.73   Mean   : -1.668   Mean   : 374.2  
 3rd Qu.:  0.00000   3rd Qu.:42.11   3rd Qu.:  1.296   3rd Qu.: 639.0  
 Max.   :299.00000   Max.   :43.57   Max.   :  4.216   Max.   :2143.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin              precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.000   Min.   :  0.00  
 1st Qu.:13.00   1st Qu.:  26.00   1st Qu.: -36.000   1st Qu.:  4.00  
 Median :26.00   Median :  70.00   Median :   5.000   Median : 21.00  
 Mean   :26.51   Mean   :  74.19   Mean   :   6.032   Mean   : 33.88  
 3rd Qu.:41.00   3rd Qu.: 124.00   3rd Qu.:  52.000   3rd Qu.: 49.00  
 Max.   :53.00   Max.   : 232.00   Max.   : 148.000   Max.   :256.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.2717  
 Mean   :0   Mean   :   9.254   Mean   :42.29   Mean   :  0.8465  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   : 953  
 1st Qu.:1971  
 Median :2247  
 Mean   :2187  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   :-21.0   Min.   :-68.00   Min.   :159.0   Min.   :0  
 1st Qu.:13.00   1st Qu.:122.0   1st Qu.: 61.00   1st Qu.:183.0   1st Qu.:0  
 Median :41.00   Median :154.0   Median : 91.00   Median :208.0   Median :0  
 Mean   :30.84   Mean   :155.3   Mean   : 88.98   Mean   :232.1   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:190.0   3rd Qu.:119.00   3rd Qu.:255.0   3rd Qu.:0  
 Max.   :53.00   Max.   :331.0   Max.   :226.00   Max.   :690.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -7.456   1st Qu.:  44.0  
 Median :  0.000   Median :42.08   Median : -1.787   Median : 251.0  
 Mean   :  2.375   Mean   :40.91   Mean   : -2.938   Mean   : 416.9  
 3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.:  1.331   3rd Qu.: 445.0  
 Max.   :685.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : -3.0   Min.   :-51.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:149.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.29   Mean   :229.6   Mean   :165.2   Mean   :  5.422   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :167.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.03   Mean   : 369.5  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   : 1.00   Min.   :-31.0   Min.   :-161.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 9.00   1st Qu.:134.0   1st Qu.:  34.00   1st Qu.:  0.00   1st Qu.:0  
 Median :18.00   Median :170.0   Median :  69.00   Median :  7.00   Median :0  
 Mean   :23.84   Mean   :172.2   Mean   :  67.73   Mean   : 19.92   Mean   :0  
 3rd Qu.:43.00   3rd Qu.:210.0   3rd Qu.: 102.00   3rd Qu.: 28.00   3rd Qu.:0  
 Max.   :53.00   Max.   :407.0   Max.   : 247.00   Max.   :172.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :28.46   Min.   :-16.329   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.07   1st Qu.: -3.919   1st Qu.:  68.6  
 Median :  0.00000   Median :41.38   Median : -1.169   Median : 353.0  
 Mean   :  0.09678   Mean   :40.86   Mean   : -1.476   Mean   : 423.8  
 3rd Qu.:  0.00000   3rd Qu.:42.14   3rd Qu.:  1.401   3rd Qu.: 704.0  
 Max.   :299.00000   Max.   :43.57   Max.   :  4.216   Max.   :2143.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin              precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.000   Min.   :  0.00  
 1st Qu.:13.00   1st Qu.:  26.00   1st Qu.: -36.000   1st Qu.:  4.00  
 Median :26.00   Median :  70.00   Median :   5.000   Median : 21.00  
 Mean   :26.51   Mean   :  74.19   Mean   :   6.032   Mean   : 33.88  
 3rd Qu.:41.00   3rd Qu.: 124.00   3rd Qu.:  52.000   3rd Qu.: 49.00  
 Max.   :53.00   Max.   : 232.00   Max.   : 148.000   Max.   :256.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.2717  
 Mean   :0   Mean   :   9.254   Mean   :42.29   Mean   :  0.8465  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   : 953  
 1st Qu.:1971  
 Median :2247  
 Mean   :2187  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt         tmax            tmin           precip         nevada 
 Min.   :13.0   Min.   :129.0   Min.   : 27.0   Min.   : 0.0   Min.   :0  
 1st Qu.:27.0   1st Qu.:256.0   1st Qu.:140.0   1st Qu.: 0.0   1st Qu.:0  
 Median :32.0   Median :289.0   Median :166.0   Median : 0.0   Median :0  
 Mean   :32.1   Mean   :285.4   Mean   :165.8   Mean   : 5.2   Mean   :0  
 3rd Qu.:37.0   3rd Qu.:316.0   3rd Qu.:192.0   3rd Qu.: 6.0   3rd Qu.:0  
 Max.   :52.0   Max.   :442.0   Max.   :272.0   Max.   :71.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :0.000000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:0.000000   1st Qu.:38.95   1st Qu.:-5.3456   1st Qu.:  35.0  
 Median :0.000000   Median :41.10   Median :-1.8606   Median : 127.0  
 Mean   :0.001355   Mean   :40.48   Mean   :-2.0703   Mean   : 270.5  
 3rd Qu.:0.000000   3rd Qu.:41.99   3rd Qu.: 0.8856   3rd Qu.: 513.0  
 Max.   :7.000000   Max.   :43.57   Max.   : 4.2156   Max.   :1167.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   :-21.0   Min.   :-68.00   Min.   :159.0   Min.   :0  
 1st Qu.:13.00   1st Qu.:122.0   1st Qu.: 61.00   1st Qu.:183.0   1st Qu.:0  
 Median :41.00   Median :154.0   Median : 91.00   Median :208.0   Median :0  
 Mean   :30.84   Mean   :155.3   Mean   : 88.98   Mean   :232.1   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:190.0   3rd Qu.:119.00   3rd Qu.:255.0   3rd Qu.:0  
 Max.   :53.00   Max.   :331.0   Max.   :226.00   Max.   :690.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -7.456   1st Qu.:  44.0  
 Median :  0.000   Median :42.08   Median : -1.787   Median : 251.0  
 Mean   :  2.375   Mean   :40.91   Mean   : -2.938   Mean   : 416.9  
 3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.:  1.331   3rd Qu.: 445.0  
 Max.   :685.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   : -3.0   Min.   :-51.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:211.0   1st Qu.:149.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :26.29   Mean   :229.6   Mean   :165.2   Mean   :  5.422   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :167.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.35   Mean   :-16.03   Mean   : 369.5  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip          nevada 
 Min.   : 1.00   Min.   :-22.0   Min.   :-161.00   Min.   : 0.00   Min.   :0  
 1st Qu.: 7.00   1st Qu.:141.0   1st Qu.:  34.00   1st Qu.: 0.00   1st Qu.:0  
 Median :13.00   Median :178.0   Median :  71.00   Median : 5.00   Median :0  
 Mean   :14.11   Mean   :178.6   Mean   :  67.74   Mean   :10.95   Mean   :0  
 3rd Qu.:19.00   3rd Qu.:219.0   3rd Qu.: 103.00   3rd Qu.:17.00   3rd Qu.:0  
 Max.   :47.00   Max.   :336.0   Max.   : 195.00   Max.   :79.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.07   1st Qu.:-3.919   1st Qu.:  69.0  
 Median :  0.00000   Median :41.32   Median :-1.117   Median : 370.0  
 Mean   :  0.09987   Mean   :40.83   Mean   :-1.432   Mean   : 447.3  
 3rd Qu.:  0.00000   3rd Qu.:42.11   3rd Qu.: 1.384   3rd Qu.: 779.0  
 Max.   :299.00000   Max.   :43.57   Max.   : 4.216   Max.   :2143.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin              precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.000   Min.   :  0.00  
 1st Qu.:13.00   1st Qu.:  26.00   1st Qu.: -36.000   1st Qu.:  4.00  
 Median :26.00   Median :  70.00   Median :   5.000   Median : 21.00  
 Mean   :26.51   Mean   :  74.19   Mean   :   6.032   Mean   : 33.88  
 3rd Qu.:41.00   3rd Qu.: 124.00   3rd Qu.:  52.000   3rd Qu.: 49.00  
 Max.   :53.00   Max.   : 232.00   Max.   : 148.000   Max.   :256.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.2717  
 Mean   :0   Mean   :   9.254   Mean   :42.29   Mean   :  0.8465  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   : 953  
 1st Qu.:1971  
 Median :2247  
 Mean   :2187  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt         tmax            tmin           precip         nevada 
 Min.   :13.0   Min.   :129.0   Min.   : 27.0   Min.   : 0.0   Min.   :0  
 1st Qu.:27.0   1st Qu.:256.0   1st Qu.:140.0   1st Qu.: 0.0   1st Qu.:0  
 Median :32.0   Median :289.0   Median :166.0   Median : 0.0   Median :0  
 Mean   :32.1   Mean   :285.4   Mean   :165.8   Mean   : 5.2   Mean   :0  
 3rd Qu.:37.0   3rd Qu.:316.0   3rd Qu.:192.0   3rd Qu.: 6.0   3rd Qu.:0  
 Max.   :52.0   Max.   :442.0   Max.   :272.0   Max.   :71.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :0.000000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:0.000000   1st Qu.:38.95   1st Qu.:-5.3456   1st Qu.:  35.0  
 Median :0.000000   Median :41.10   Median :-1.8606   Median : 127.0  
 Mean   :0.001355   Mean   :40.48   Mean   :-2.0703   Mean   : 270.5  
 3rd Qu.:0.000000   3rd Qu.:41.99   3rd Qu.: 0.8856   3rd Qu.: 513.0  
 Max.   :7.000000   Max.   :43.57   Max.   : 4.2156   Max.   :1167.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax          tmin             precip           nevada 
 Min.   : 1.00   Min.   :-31   Min.   :-155.00   Min.   :  0.00   Min.   :0  
 1st Qu.:41.00   1st Qu.:125   1st Qu.:  33.00   1st Qu.:  1.00   1st Qu.:0  
 Median :46.00   Median :158   Median :  66.00   Median : 19.00   Median :0  
 Mean   :41.03   Mean   :161   Mean   :  67.71   Mean   : 35.76   Mean   :0  
 3rd Qu.:49.00   3rd Qu.:191   3rd Qu.: 100.00   3rd Qu.: 62.00   3rd Qu.:0  
 Max.   :53.00   Max.   :407   Max.   : 247.00   Max.   :172.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :  0.00000   Min.   :28.46   Min.   :-16.329   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.30   1st Qu.: -4.049   1st Qu.:  61.0  
 Median :  0.00000   Median :41.48   Median : -1.229   Median : 287.0  
 Mean   :  0.09131   Mean   :40.91   Mean   : -1.555   Mean   : 382.3  
 3rd Qu.:  0.00000   3rd Qu.:42.23   3rd Qu.:  1.401   3rd Qu.: 639.0  
 Max.   :290.00000   Max.   :43.57   Max.   :  4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   :-21.0   Min.   :-68.00   Min.   :159.0   Min.   :0  
 1st Qu.:13.00   1st Qu.:122.0   1st Qu.: 61.00   1st Qu.:183.0   1st Qu.:0  
 Median :41.00   Median :154.0   Median : 91.00   Median :208.0   Median :0  
 Mean   :30.84   Mean   :155.3   Mean   : 88.98   Mean   :232.1   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:190.0   3rd Qu.:119.00   3rd Qu.:255.0   3rd Qu.:0  
 Max.   :53.00   Max.   :331.0   Max.   :226.00   Max.   :690.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -7.456   1st Qu.:  44.0  
 Median :  0.000   Median :42.08   Median : -1.787   Median : 251.0  
 Mean   :  2.375   Mean   :40.91   Mean   : -2.938   Mean   : 416.9  
 3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.:  1.331   3rd Qu.: 445.0  
 Max.   :685.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip            nevada 
 Min.   : 1.00   Min.   : -3.0   Min.   :-51.00   Min.   :  0.000   Min.   :0  
 1st Qu.:13.75   1st Qu.:101.0   1st Qu.: 28.00   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :140.0   Median : 61.00   Median :  0.000   Median :0  
 Mean   :26.39   Mean   :144.7   Mean   : 68.33   Mean   :  7.374   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:191.0   3rd Qu.:109.00   3rd Qu.:  3.000   3rd Qu.:0  
 Max.   :53.00   Max.   :263.0   Max.   :184.00   Max.   :165.000   Max.   :0  
   prof_nieve    longitud        latitud         altitud    
 Min.   :0    Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.:0    1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median :0    Median :28.31   Median :-16.5   Median :2371  
 Mean   :0    Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.:0    3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :0    Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip          nevada 
 Min.   : 1.00   Min.   :-22.0   Min.   :-161.00   Min.   : 0.00   Min.   :0  
 1st Qu.: 7.00   1st Qu.:141.0   1st Qu.:  34.00   1st Qu.: 0.00   1st Qu.:0  
 Median :13.00   Median :178.0   Median :  71.00   Median : 5.00   Median :0  
 Mean   :14.11   Mean   :178.6   Mean   :  67.74   Mean   :10.95   Mean   :0  
 3rd Qu.:19.00   3rd Qu.:219.0   3rd Qu.: 103.00   3rd Qu.:17.00   3rd Qu.:0  
 Max.   :47.00   Max.   :336.0   Max.   : 195.00   Max.   :79.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:40.07   1st Qu.:-3.919   1st Qu.:  69.0  
 Median :  0.00000   Median :41.32   Median :-1.117   Median : 370.0  
 Mean   :  0.09987   Mean   :40.83   Mean   :-1.432   Mean   : 447.3  
 3rd Qu.:  0.00000   3rd Qu.:42.11   3rd Qu.: 1.384   3rd Qu.: 779.0  
 Max.   :299.00000   Max.   :43.57   Max.   : 4.216   Max.   :2143.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin              precip      
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.000   Min.   :  0.00  
 1st Qu.:13.00   1st Qu.:  26.00   1st Qu.: -36.000   1st Qu.:  4.00  
 Median :26.00   Median :  70.00   Median :   5.000   Median : 21.00  
 Mean   :26.51   Mean   :  74.19   Mean   :   6.032   Mean   : 33.88  
 3rd Qu.:41.00   3rd Qu.: 124.00   3rd Qu.:  52.000   3rd Qu.: 49.00  
 Max.   :53.00   Max.   : 232.00   Max.   : 148.000   Max.   :256.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.:  0.7789  
 Median :0   Median :   0.000   Median :42.47   Median :  1.2717  
 Mean   :0   Mean   :   9.254   Mean   :42.29   Mean   :  0.8465  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.:  1.7150  
 Max.   :0   Max.   :1073.000   Max.   :42.77   Max.   :  2.4378  
    altitud    
 Min.   : 953  
 1st Qu.:1971  
 Median :2247  
 Mean   :2187  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   :126.0   Min.   : 67.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:218.0   1st Qu.:157.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :239.0   Median :177.0   Median :  0.000   Median :0  
 Mean   :26.28   Mean   :240.6   Mean   :177.8   Mean   :  5.168   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:265.0   3rd Qu.:205.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :167.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud   
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   : 14  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-17.75   1st Qu.: 25  
 Median :0    Median :28.46   Median :-16.33   Median : 33  
 Mean   :0    Mean   :28.36   Mean   :-15.97   Mean   :110  
 3rd Qu.:0    3rd Qu.:28.63   3rd Qu.:-13.86   3rd Qu.: 64  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :632  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt         tmax            tmin           precip         nevada 
 Min.   :13.0   Min.   :129.0   Min.   : 27.0   Min.   : 0.0   Min.   :0  
 1st Qu.:27.0   1st Qu.:256.0   1st Qu.:140.0   1st Qu.: 0.0   1st Qu.:0  
 Median :32.0   Median :289.0   Median :166.0   Median : 0.0   Median :0  
 Mean   :32.1   Mean   :285.4   Mean   :165.8   Mean   : 5.2   Mean   :0  
 3rd Qu.:37.0   3rd Qu.:316.0   3rd Qu.:192.0   3rd Qu.: 6.0   3rd Qu.:0  
 Max.   :52.0   Max.   :442.0   Max.   :272.0   Max.   :71.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :0.000000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:0.000000   1st Qu.:38.95   1st Qu.:-5.3456   1st Qu.:  35.0  
 Median :0.000000   Median :41.10   Median :-1.8606   Median : 127.0  
 Mean   :0.001355   Mean   :40.48   Mean   :-2.0703   Mean   : 270.5  
 3rd Qu.:0.000000   3rd Qu.:41.99   3rd Qu.: 0.8856   3rd Qu.: 513.0  
 Max.   :7.000000   Max.   :43.57   Max.   : 4.2156   Max.   :1167.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 1.00   Min.   : 29.0   Min.   :-36.0   Min.   : 26.00   Min.   :0  
 1st Qu.:15.00   1st Qu.:143.0   1st Qu.: 67.0   1st Qu.: 59.00   1st Qu.:0  
 Median :29.00   Median :181.0   Median : 99.0   Median : 76.00   Median :0  
 Mean   :28.23   Mean   :187.2   Mean   :100.4   Mean   : 81.74   Mean   :0  
 3rd Qu.:42.00   3rd Qu.:229.0   3rd Qu.:134.0   3rd Qu.: 99.00   3rd Qu.:0  
 Max.   :53.00   Max.   :407.0   Max.   :247.0   Max.   :172.00   Max.   :0  
   prof_nieve        longitud        latitud           altitud      
 Min.   : 0.000   Min.   :28.46   Min.   :-16.329   Min.   :   1.0  
 1st Qu.: 0.000   1st Qu.:40.95   1st Qu.: -4.049   1st Qu.:  52.0  
 Median : 0.000   Median :41.84   Median : -1.033   Median : 251.0  
 Mean   : 0.113   Mean   :41.46   Mean   : -1.568   Mean   : 323.1  
 3rd Qu.: 0.000   3rd Qu.:42.70   3rd Qu.:  1.768   3rd Qu.: 515.0  
 Max.   :73.000   Max.   :43.57   Max.   :  4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   :-21.0   Min.   :-68.00   Min.   :159.0   Min.   :0  
 1st Qu.:13.00   1st Qu.:122.0   1st Qu.: 61.00   1st Qu.:183.0   1st Qu.:0  
 Median :41.00   Median :154.0   Median : 91.00   Median :208.0   Median :0  
 Mean   :30.84   Mean   :155.3   Mean   : 88.98   Mean   :232.1   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:190.0   3rd Qu.:119.00   3rd Qu.:255.0   3rd Qu.:0  
 Max.   :53.00   Max.   :331.0   Max.   :226.00   Max.   :690.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -7.456   1st Qu.:  44.0  
 Median :  0.000   Median :42.08   Median : -1.787   Median : 251.0  
 Mean   :  2.375   Mean   :40.91   Mean   : -2.938   Mean   : 416.9  
 3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.:  1.331   3rd Qu.: 445.0  
 Max.   :685.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax          tmin             precip          nevada 
 Min.   :31.00   Min.   :-31   Min.   :-155.00   Min.   : 0.00   Min.   :0  
 1st Qu.:46.00   1st Qu.:117   1st Qu.:  21.00   1st Qu.: 0.00   1st Qu.:0  
 Median :48.00   Median :149   Median :  51.00   Median : 3.00   Median :0  
 Mean   :47.84   Mean   :147   Mean   :  50.32   Mean   :11.26   Mean   :0  
 3rd Qu.:50.00   3rd Qu.:177   3rd Qu.:  80.00   3rd Qu.:18.00   3rd Qu.:0  
 Max.   :53.00   Max.   :297   Max.   : 189.00   Max.   :76.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:39.49   1st Qu.:-4.049   1st Qu.:  69.0  
 Median :  0.00000   Median :41.19   Median :-1.293   Median : 359.0  
 Mean   :  0.07977   Mean   :40.61   Mean   :-1.549   Mean   : 413.9  
 3rd Qu.:  0.00000   3rd Qu.:41.98   3rd Qu.: 1.331   3rd Qu.: 687.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip            nevada 
 Min.   : 1.00   Min.   : -3.0   Min.   :-51.00   Min.   :  0.000   Min.   :0  
 1st Qu.:13.75   1st Qu.:101.0   1st Qu.: 28.00   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :140.0   Median : 61.00   Median :  0.000   Median :0  
 Mean   :26.39   Mean   :144.7   Mean   : 68.33   Mean   :  7.374   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:191.0   3rd Qu.:109.00   3rd Qu.:  3.000   3rd Qu.:0  
 Max.   :53.00   Max.   :263.0   Max.   :184.00   Max.   :165.000   Max.   :0  
   prof_nieve    longitud        latitud         altitud    
 Min.   :0    Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.:0    1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median :0    Median :28.31   Median :-16.5   Median :2371  
 Mean   :0    Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.:0    3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :0    Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   : 66.0   Min.   :-28.00   Min.   : 0.00   Min.   :0  
 1st Qu.: 9.00   1st Qu.:167.0   1st Qu.: 61.00   1st Qu.: 0.00   1st Qu.:0  
 Median :15.00   Median :196.0   Median : 86.00   Median : 4.00   Median :0  
 Mean   :16.43   Mean   :198.9   Mean   : 86.47   Mean   :10.87   Mean   :0  
 3rd Qu.:21.00   3rd Qu.:230.0   3rd Qu.:112.00   3rd Qu.:17.00   3rd Qu.:0  
 Max.   :47.00   Max.   :336.0   Max.   :195.00   Max.   :73.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:39.49   1st Qu.:-4.010   1st Qu.:  43.0  
 Median :  0.00000   Median :41.22   Median :-0.558   Median : 185.0  
 Mean   :  0.03217   Mean   :40.68   Mean   :-1.396   Mean   : 370.9  
 3rd Qu.:  0.00000   3rd Qu.:42.08   3rd Qu.: 1.418   3rd Qu.: 674.0  
 Max.   :173.00000   Max.   :43.57   Max.   : 4.216   Max.   :2143.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin              precip     
 Min.   : 1.000   Min.   :-22.0   Min.   :-161.000   Min.   : 0.00  
 1st Qu.: 3.000   1st Qu.: 92.0   1st Qu.: -11.000   1st Qu.: 0.00  
 Median : 6.000   Median :115.0   Median :   9.000   Median : 5.00  
 Mean   : 6.527   Mean   :112.5   Mean   :   6.714   Mean   :11.21  
 3rd Qu.: 9.000   3rd Qu.:135.0   3rd Qu.:  27.000   3rd Qu.:17.00  
 Max.   :28.000   Max.   :217.0   Max.   :  89.000   Max.   :79.00  
     nevada    prof_nieve          longitud        latitud      
 Min.   :0   Min.   :  0.0000   Min.   :36.64   Min.   :-8.624  
 1st Qu.:0   1st Qu.:  0.0000   1st Qu.:40.66   1st Qu.:-3.789  
 Median :0   Median :  0.0000   Median :41.60   Median :-1.861  
 Mean   :0   Mean   :  0.3204   Mean   :41.30   Mean   :-1.549  
 3rd Qu.:0   3rd Qu.:  0.0000   3rd Qu.:42.11   3rd Qu.: 1.179  
 Max.   :0   Max.   :299.0000   Max.   :43.36   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.: 515.0  
 Median : 687.0  
 Mean   : 696.2  
 3rd Qu.: 890.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax              tmin              precip     
 Min.   : 1.00   Min.   :-109.00   Min.   :-189.000   Min.   : 0.00  
 1st Qu.:12.00   1st Qu.:  31.00   1st Qu.: -33.000   1st Qu.: 3.00  
 Median :26.00   Median :  76.00   Median :   8.000   Median :15.00  
 Mean   :26.25   Mean   :  78.97   Mean   :   9.344   Mean   :21.04  
 3rd Qu.:40.00   3rd Qu.: 131.00   3rd Qu.:  57.000   3rd Qu.:35.00  
 Max.   :53.00   Max.   : 232.00   Max.   : 148.000   Max.   :88.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :  0.000   Min.   :40.78   Min.   :-4.0103   Min.   :1002  
 1st Qu.:0   1st Qu.:  0.000   1st Qu.:42.29   1st Qu.: 0.7789   1st Qu.:1971  
 Median :0   Median :  0.000   Median :42.47   Median : 1.2717   Median :2247  
 Mean   :0   Mean   :  7.657   Mean   :42.30   Mean   : 0.8959   Mean   :2189  
 3rd Qu.:0   3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.: 1.7150   3rd Qu.:2400  
 Max.   :0   Max.   :985.000   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 1.00   Min.   :126.0   Min.   : 67.0   Min.   :  0.000   Min.   :0  
 1st Qu.:13.00   1st Qu.:218.0   1st Qu.:157.0   1st Qu.:  0.000   1st Qu.:0  
 Median :26.00   Median :239.0   Median :177.0   Median :  0.000   Median :0  
 Mean   :26.28   Mean   :240.6   Mean   :177.8   Mean   :  5.168   Mean   :0  
 3rd Qu.:39.00   3rd Qu.:265.0   3rd Qu.:205.0   3rd Qu.:  2.000   3rd Qu.:0  
 Max.   :53.00   Max.   :384.0   Max.   :263.0   Max.   :167.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud   
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   : 14  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-17.75   1st Qu.: 25  
 Median :0    Median :28.46   Median :-16.33   Median : 33  
 Mean   :0    Mean   :28.36   Mean   :-15.97   Mean   :110  
 3rd Qu.:0    3rd Qu.:28.63   3rd Qu.:-13.86   3rd Qu.: 64  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :632  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax             tmin             precip          nevada 
 Min.   : 1.00   Min.   :-69.00   Min.   :-131.00   Min.   : 47.0   Min.   :0  
 1st Qu.:15.00   1st Qu.:  8.00   1st Qu.: -49.00   1st Qu.: 83.0   1st Qu.:0  
 Median :23.00   Median : 42.00   Median : -12.50   Median :102.0   Median :0  
 Mean   :28.06   Mean   : 45.84   Mean   : -13.65   Mean   :110.2   Mean   :0  
 3rd Qu.:44.00   3rd Qu.: 82.00   3rd Qu.:  19.00   3rd Qu.:130.0   3rd Qu.:0  
 Max.   :53.00   Max.   :205.00   Max.   : 115.00   Max.   :256.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud    
 Min.   :   0.00   Min.   :28.31   Min.   :-16.4992   Min.   : 953  
 1st Qu.:   0.00   1st Qu.:42.18   1st Qu.:  0.7789   1st Qu.:1971  
 Median :   0.00   Median :42.47   Median :  1.0544   Median :2247  
 Mean   :  18.74   Mean   :42.22   Mean   :  0.5530   Mean   :2171  
 3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.:  1.5242   3rd Qu.:2400  
 Max.   :1073.00   Max.   :42.77   Max.   :  2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt         tmax            tmin           precip         nevada 
 Min.   :13.0   Min.   :129.0   Min.   : 27.0   Min.   : 0.0   Min.   :0  
 1st Qu.:27.0   1st Qu.:256.0   1st Qu.:140.0   1st Qu.: 0.0   1st Qu.:0  
 Median :32.0   Median :289.0   Median :166.0   Median : 0.0   Median :0  
 Mean   :32.1   Mean   :285.4   Mean   :165.8   Mean   : 5.2   Mean   :0  
 3rd Qu.:37.0   3rd Qu.:316.0   3rd Qu.:192.0   3rd Qu.: 6.0   3rd Qu.:0  
 Max.   :52.0   Max.   :442.0   Max.   :272.0   Max.   :71.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :0.000000   Min.   :35.28   Min.   :-8.6239   Min.   :   1.0  
 1st Qu.:0.000000   1st Qu.:38.95   1st Qu.:-5.3456   1st Qu.:  35.0  
 Median :0.000000   Median :41.10   Median :-1.8606   Median : 127.0  
 Mean   :0.001355   Mean   :40.48   Mean   :-2.0703   Mean   : 270.5  
 3rd Qu.:0.000000   3rd Qu.:41.99   3rd Qu.: 0.8856   3rd Qu.: 513.0  
 Max.   :7.000000   Max.   :43.57   Max.   : 4.2156   Max.   :1167.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 1.00   Min.   : 29.0   Min.   :-36.0   Min.   : 26.00   Min.   :0  
 1st Qu.:15.00   1st Qu.:143.0   1st Qu.: 67.0   1st Qu.: 59.00   1st Qu.:0  
 Median :29.00   Median :181.0   Median : 99.0   Median : 76.00   Median :0  
 Mean   :28.23   Mean   :187.2   Mean   :100.4   Mean   : 81.74   Mean   :0  
 3rd Qu.:42.00   3rd Qu.:229.0   3rd Qu.:134.0   3rd Qu.: 99.00   3rd Qu.:0  
 Max.   :53.00   Max.   :407.0   Max.   :247.0   Max.   :172.00   Max.   :0  
   prof_nieve        longitud        latitud           altitud      
 Min.   : 0.000   Min.   :28.46   Min.   :-16.329   Min.   :   1.0  
 1st Qu.: 0.000   1st Qu.:40.95   1st Qu.: -4.049   1st Qu.:  52.0  
 Median : 0.000   Median :41.84   Median : -1.033   Median : 251.0  
 Mean   : 0.113   Mean   :41.46   Mean   : -1.568   Mean   : 323.1  
 3rd Qu.: 0.000   3rd Qu.:42.70   3rd Qu.:  1.768   3rd Qu.: 515.0  
 Max.   :73.000   Max.   :43.57   Max.   :  4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   :-21.0   Min.   :-68.00   Min.   :159.0   Min.   :0  
 1st Qu.:13.00   1st Qu.:122.0   1st Qu.: 61.00   1st Qu.:183.0   1st Qu.:0  
 Median :41.00   Median :154.0   Median : 91.00   Median :208.0   Median :0  
 Mean   :30.84   Mean   :155.3   Mean   : 88.98   Mean   :232.1   Mean   :0  
 3rd Qu.:45.00   3rd Qu.:190.0   3rd Qu.:119.00   3rd Qu.:255.0   3rd Qu.:0  
 Max.   :53.00   Max.   :331.0   Max.   :226.00   Max.   :690.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -7.456   1st Qu.:  44.0  
 Median :  0.000   Median :42.08   Median : -1.787   Median : 251.0  
 Mean   :  2.375   Mean   :40.91   Mean   : -2.938   Mean   : 416.9  
 3rd Qu.:  0.000   3rd Qu.:42.64   3rd Qu.:  1.331   3rd Qu.: 445.0  
 Max.   :685.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax          tmin             precip          nevada 
 Min.   :31.00   Min.   :-31   Min.   :-155.00   Min.   : 0.00   Min.   :0  
 1st Qu.:46.00   1st Qu.:117   1st Qu.:  21.00   1st Qu.: 0.00   1st Qu.:0  
 Median :48.00   Median :149   Median :  51.00   Median : 3.00   Median :0  
 Mean   :47.84   Mean   :147   Mean   :  50.32   Mean   :11.26   Mean   :0  
 3rd Qu.:50.00   3rd Qu.:177   3rd Qu.:  80.00   3rd Qu.:18.00   3rd Qu.:0  
 Max.   :53.00   Max.   :297   Max.   : 189.00   Max.   :76.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :  0.00000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:  0.00000   1st Qu.:39.49   1st Qu.:-4.049   1st Qu.:  69.0  
 Median :  0.00000   Median :41.19   Median :-1.293   Median : 359.0  
 Mean   :  0.07977   Mean   :40.61   Mean   :-1.549   Mean   : 413.9  
 3rd Qu.:  0.00000   3rd Qu.:41.98   3rd Qu.: 1.331   3rd Qu.: 687.0  
 Max.   :290.00000   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)